SOTAVerified

Feature Compression

Compress data for machine interpretability to perform downstream tasks, rather than for human perception.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–96 of 96 papers

TitleStatusHype
DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality—0
In Defense of Clip-based Video Relation Detection—0
End-to-End Learnable Multi-Scale Feature Compression for VCM—0
Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization—0
SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network AcceleratorsCode0
Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression—0
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing—0
Supervised Feature Compression based on Counterfactual AnalysisCode0
Efficient Feature Compression for Edge-Cloud SystemsCode0
Cross Modal Compression: Towards Human-comprehensible Semantic Compression—0
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation—0
Feature Compression for Rate Constrained Object Detection on the Edge—0
SC2 Benchmark: Supervised Compression for Split ComputingCode0
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Source Feature Compression for Object Classification in Vision-Based Underwater Robotics—0
Reconstructing Pruned Filters using Cheap Spatial Transformations—0
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics—0
Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression—0
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks—0
Communication-Computation Efficient Device-Edge Co-Inference via AutoML—0
Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information—0
Fusion: Towards Automated ICD Coding via Feature Compression—0
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search—0
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic—0
Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective—0
Selective Feature Compression for Efficient Activity Recognition Inference—0
Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction—0
Collaborative Intelligence: Challenges and Opportunities—0
Dynamic Submodular Maximization—0
PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection—0
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning—0
Chromatic Learning for Sparse Datasets—0
Joint Device-Edge Inference over Wireless Links with Pruning—0
End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement—0
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics—0
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal—0
BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference SystemsCode0
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks—0
Categorical Feature Compression via Submodular Optimization—0
Comparing of Term Clustering Frameworks for Modular Ontology Learning—0
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing—0
Near-Lossless Deep Feature Compression for Collaborative Intelligence—0
Context-aware Deep Feature Compression for High-speed Visual TrackingCode0
Deep feature compression for collaborative object detection—0
Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks—0
Compact Representation for Image Classification: To Choose or to Compress?—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.